© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 50912
    Prev
    Next
    INDEX
    Explanations

    connecting ideas or listing options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     a
    0.52
    rogens
    0.50
     (
    0.47
    “
    0.47
    }
    0.46
     résultats
    0.45
     \
    0.43
     –
    0.43
     this
    0.42
    《
    0.42
    POSITIVE LOGITS
     এবং
    0.97
     மற்றும்
    0.96
     και
    0.95
     మరియు
    0.95
     आणि
    0.93
    and
    0.93
    และ
    0.92
     और
    0.89
     и
    0.89
    및
    0.87
    Activations Density 0.002%

    No Known Activations